Deep Learning Models for Gunshot Detection in the Albufera Natural Park

Gunshot detection in natural environments is crucial for the protection of endangered species. In this work, we present a novel dataset built from the soundscape recording at five different locations of the Spanish Albufera National Park. We then carry out an experimental study to detect gunshots from the rest of the background sounds and noises labeled as “vbackground”. For this purpose, we perform comprehensive experiments both in the data input and the modeling stages of three efficient deep convolutional neural networks (DCNNs), obtaining an F1 score (harmonic mean of precision and recall) of 0.92 for the best model. The best three DCNNs are also used to monitor one hour of the Albufera soundscape where the gunshot class represents 8 % of the testset. The recall values obtained with our model are comparable to previous works monitoring gunshots in real scenarios.